As an emerging technology and a relatively affordable device, the 4D imaging radar has already been confirmed effective in performing 3D object detection in autonomous driving. Nevertheless, the sparsity and noisiness of 4D radar point clouds hinder further performance improvement, and in-depth studies about its fusion with other modalities are lacking. On the other hand, as a new image view transformation strategy, “sampling” has been applied in a few image-based detectors and shown to outperform the widely applied “depth-based splatting” proposed in Lift-Splat-Shoot (LSS), even without image depth prediction. However, the potential of “sampling” is not fully unleashed. This article investigates the “sampling” view transformation strategy on the camera and 4D imaging radar fusion-based 3D object detection. In the proposed LiDAR Excluded Lean (LXL) model, predicted image depth distribution maps and radar 3D occupancy grids are generated from image perspective view (PV) features and radar bird's eye view (BEV) features, respectively. They are sent to the core of LXL, called “radar occupancy-assisted depth-based sampling”, to aid image view transformation. We demonstrated that more accurate view transformation can be performed by introducing image depths and radar information to enhance the “sampling” strategy. Experiments on VoD and TJ4DRadSet datasets show that the proposed method outperforms the state-of-the-art 3D object detection methods by a significant margin without bells and whistles. Ablation studies demonstrate that our method performs the best among different enhancement settings.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    LXL: LiDAR Excluded Lean 3D Object Detection With 4D Imaging Radar and Camera Fusion


    Beteiligte:
    Xiong, Weiyi (Autor:in) / Liu, Jianan (Autor:in) / Huang, Tao (Autor:in) / Han, Qing-Long (Autor:in) / Xia, Yuxuan (Autor:in) / Zhu, Bing (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    01.01.2024


    Format / Umfang :

    2947495 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    LXL: LiDAR Excluded Lean 3D Object Detection with 4D Imaging Radar and Camera Fusion

    Xiong, Weiyi / Liu, Jianan / Huang, Tao et al. | IEEE | 2024


    RADAR LIDAR OBJECT DETECTION USING RADAR AND LIDAR FUSION

    MENG XIAOLI / ZHOU LUBING / SHETTI KARAN RAJENDRA | Europäisches Patentamt | 2023

    Freier Zugriff

    Deep Learning-based Radar, Camera, and Lidar Fusion for Object Detection

    Nobis, Felix Otto Geronimo | TIBKAT | 2022

    Freier Zugriff

    Radar-Lidar Fusion for Object Detection by Designing Effective Convolution Networks

    Munir, Farzeen / Azam, Shoaib / Kucner, Tomasz et al. | IEEE | 2023


    Multi-Object Tracking with Object Candidate Fusion for Camera and LiDAR Data

    Yin, Huilin / Lu, Yu / Lin, Jia et al. | IEEE | 2023